Towards operator 4.0, increasing production efficiency and reducing operator workload by process mining of alarm data

Gyula Dörgo, Kristof Varga, Máté Haragovics, Tibor Szabó, J. Abonyi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A methodology to extract temporal patterns of alarm sequences and operator actions from the log files of alarm management systems is proposed. Firstly, time-segments that are informative from the viewpoint of operator interventions are identified by the algorithm. These segments include series of alarms that initialize operator actions, sets of operator actions, and a period that potentially covers the effects of the corrective actions of the operators. In the second step of the methodology, the sets of operator actions that are frequently applied in the same situations are determined. For this purpose, the FP-Growth Algorithm, which is one of the fastest tools of frequent item-set mining and generates well-structured action trees that are not only suitable for the visualization of interventions but lend themselves to build association rules that could be directly applied in decision support systems, is utilized. Finally, multi-temporal sequence mining is applied to reveal what alarms led to the sets of operator actions and what were the effects of these interventions. The applicability of the methodology is illustrated by presenting results connected to the analysis of the delayed coker plant at the Danube Refinery of the MOL Group.

Original languageEnglish
Pages (from-to)829-834
Number of pages6
JournalChemical Engineering Transactions
Volume70
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Association rules
Decision support systems
Mathematical operators
Visualization

ASJC Scopus subject areas

  • Chemical Engineering(all)

Cite this

Towards operator 4.0, increasing production efficiency and reducing operator workload by process mining of alarm data. / Dörgo, Gyula; Varga, Kristof; Haragovics, Máté; Szabó, Tibor; Abonyi, J.

In: Chemical Engineering Transactions, Vol. 70, 01.01.2018, p. 829-834.

Research output: Contribution to journalArticle

@article{83671462ec46498288cd5064bc4b8009,
title = "Towards operator 4.0, increasing production efficiency and reducing operator workload by process mining of alarm data",
abstract = "A methodology to extract temporal patterns of alarm sequences and operator actions from the log files of alarm management systems is proposed. Firstly, time-segments that are informative from the viewpoint of operator interventions are identified by the algorithm. These segments include series of alarms that initialize operator actions, sets of operator actions, and a period that potentially covers the effects of the corrective actions of the operators. In the second step of the methodology, the sets of operator actions that are frequently applied in the same situations are determined. For this purpose, the FP-Growth Algorithm, which is one of the fastest tools of frequent item-set mining and generates well-structured action trees that are not only suitable for the visualization of interventions but lend themselves to build association rules that could be directly applied in decision support systems, is utilized. Finally, multi-temporal sequence mining is applied to reveal what alarms led to the sets of operator actions and what were the effects of these interventions. The applicability of the methodology is illustrated by presenting results connected to the analysis of the delayed coker plant at the Danube Refinery of the MOL Group.",
author = "Gyula D{\"o}rgo and Kristof Varga and M{\'a}t{\'e} Haragovics and Tibor Szab{\'o} and J. Abonyi",
year = "2018",
month = "1",
day = "1",
doi = "10.3303/CET1870139",
language = "English",
volume = "70",
pages = "829--834",
journal = "Chemical Engineering Transactions",
issn = "1974-9791",
publisher = "AIDIC-Italian Association of Chemical Engineering",

}

TY - JOUR

T1 - Towards operator 4.0, increasing production efficiency and reducing operator workload by process mining of alarm data

AU - Dörgo, Gyula

AU - Varga, Kristof

AU - Haragovics, Máté

AU - Szabó, Tibor

AU - Abonyi, J.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - A methodology to extract temporal patterns of alarm sequences and operator actions from the log files of alarm management systems is proposed. Firstly, time-segments that are informative from the viewpoint of operator interventions are identified by the algorithm. These segments include series of alarms that initialize operator actions, sets of operator actions, and a period that potentially covers the effects of the corrective actions of the operators. In the second step of the methodology, the sets of operator actions that are frequently applied in the same situations are determined. For this purpose, the FP-Growth Algorithm, which is one of the fastest tools of frequent item-set mining and generates well-structured action trees that are not only suitable for the visualization of interventions but lend themselves to build association rules that could be directly applied in decision support systems, is utilized. Finally, multi-temporal sequence mining is applied to reveal what alarms led to the sets of operator actions and what were the effects of these interventions. The applicability of the methodology is illustrated by presenting results connected to the analysis of the delayed coker plant at the Danube Refinery of the MOL Group.

AB - A methodology to extract temporal patterns of alarm sequences and operator actions from the log files of alarm management systems is proposed. Firstly, time-segments that are informative from the viewpoint of operator interventions are identified by the algorithm. These segments include series of alarms that initialize operator actions, sets of operator actions, and a period that potentially covers the effects of the corrective actions of the operators. In the second step of the methodology, the sets of operator actions that are frequently applied in the same situations are determined. For this purpose, the FP-Growth Algorithm, which is one of the fastest tools of frequent item-set mining and generates well-structured action trees that are not only suitable for the visualization of interventions but lend themselves to build association rules that could be directly applied in decision support systems, is utilized. Finally, multi-temporal sequence mining is applied to reveal what alarms led to the sets of operator actions and what were the effects of these interventions. The applicability of the methodology is illustrated by presenting results connected to the analysis of the delayed coker plant at the Danube Refinery of the MOL Group.

UR - http://www.scopus.com/inward/record.url?scp=85051344271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051344271&partnerID=8YFLogxK

U2 - 10.3303/CET1870139

DO - 10.3303/CET1870139

M3 - Article

AN - SCOPUS:85051344271

VL - 70

SP - 829

EP - 834

JO - Chemical Engineering Transactions

JF - Chemical Engineering Transactions

SN - 1974-9791

ER -